Page History

...

tmpfs for sequences and compositions 

...

Problem

It's hard to pipe data between actions, when the size of the response is above the response size limits. As a result, each action in a sequence must read the asset independently, and upload any new content to a temporary storage, for the next action in the sequence to read it. This creates 2 main problems: 

• Poor developer experience
• Poor execution performance

Workarounds

Send Asset by Reference

...

• Direct action-to-action communication. The most performant option would be to allow actions to communicate directly, and ideally schedule them on the same host. The problem introduced by this approach is the network isolation. Usually OpenWhisk deployments create a network perimeter around each action, preventing it to poke other actions in the cluster. For action-to-action communication to be opened, each namespace should probably have its own network perimeter.
• Action-to-proxy-to-action. This is similar to how Kafka is being used currently. But to workaround kafka payload limits, another proxy could be used. The communication should be secured in this case as well, so that only the allowed actions can communicate.      

Higher memory limits

Problem

Some DL/ML algorithms need more memory to process a data input. Existing limits are too low.

...

TBD:  allocation implications in Scheduler / Load Balancer. 

Longer execution time 

Problem

During a clod start, an AI action may have to do a one-time initialization, such as downloading a model from the model registry. 

...